Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Som
    -0.08
    _M
    -0.07
    Som
    -0.07
     Presents
    -0.07
    fold
    -0.06
    awy
    -0.06
    .n
    -0.06
    som
    -0.06
     Alphabet
    -0.06
     Visitors
    -0.06
    POSITIVE LOGITS
     xếp
    0.08
    progressbar
    0.06
    memcpy
    0.06
     milf
    0.06
     اشاره
    0.06
     inherently
    0.06
    .BorderColor
    0.06
    _monitor
    0.06
    .bunifu
    0.06
     pointing
    0.06
    Act Density 0.036%

    No Known Activations